Skip to content

HarnessPAI: An Evolving Harness for Physical AI

Sep 2026 · 13 citations · ⚡ 2 influential · 63 references
Computer Science

TL;DR

The results suggest that the frontier of Physical AI depends not only on stronger action models, but also on executable harnesses that integrate perception, task understanding and reasoning, and action execution into a unified, verifiable, and feedback-driven system.

Abstract

Physical AI aims to build embodied agents that perceive the world, understand and reason about it, and decide how to act. Yet the field has focused primarily on the last component: the action model that maps observations to low-level controls. The prevailing training recipe can erode the perceptual and reasoning capabilities needed for robust behavior, leaving even strong action models vulnerable to scene perturbations and long-horizon tasks. We introduce HarnessPAI, a model- and embodiment-agnostic Harness framework for Physical AI that treats code as the executable and evolvable interface that organizes the underlying action primitive. The framework separates two timescales: within a rollout, it executes open-loop at the program level, with a fixed program guiding and checking execution; across rollouts, it evolves closed-loop, using execution feedback to revise the program and distill failures into reusable skills. Across desktop robot arms, household robots, a robot vacuum, and a legged walking agent, HarnessPAI demonstrates consistent improvements against baselines. Beyond the harness, the converged program also acts as a low-cost, reliable source of expert data: it generates training data for fine-tuning VLA and WAM models on tasks where it is hard for these models to obtain successful trajectories on their own. Our results suggest that the frontier of Physical AI depends not only on stronger action models, but also on executable harnesses that integrate perception, task understanding and reasoning, and action execution into a unified, verifiable, and feedback-driven system. Website: https://darwin-agent.github.io/HarnessPAI

View source

Similar papers

DynaHarness: A Dynamic Physical Harness for Self-Evolving Robot Agents

Pretrained robot policies provide useful action priors, but long-horizon manipulation still requires coordination between semantic reasoning and physical execution. Semantic reasoning operates at a coarser timescale than physical interaction, while episode-level failures provide limited guidance on which system compone...

Hao-Yuan Deng, Jie-Bin Liu, Teng-Xiao Zhang et al. · 2 citations
#artificial intelligence Preprint Oct 2026

NavGPT-3: Harnessing Context in a Hierarchical Navigation Runtime

NavGPT-3 is presented, a harness that connects the two models, with an OS-like runtime built above it: reasoning, acting, and monitoring run as threads with their own context, tools, and permissions, while the runtime schedules them and decides which thread controls the robot's motion, so that the robot can react to su...

Geng-Ze Zhou, Yicong Hong, Jiazhao Zhang et al. · 2 citations · ⚡1
#artificial intelligence Preprint Oct 2026

EmbodiedRSI: Active Continual Robot Learning Through Hypothesis-Guided Co-Evolution

Robot foundation models provide strong visuomotor control, yet their performance can degrade when object positions or task instructions change. Further improvements often require post-training on substantial robot data, which can be costly to collect through methods such as teleoperation. Agentic harnesses can adapt ar...

Python Song, Zhi-Xuan Liang, Kelsey Fu et al. · 9 citations · ⚡1
Review Sep 2026

Self-Evolving AI for Humanoids: Mechanisms, Safety, and Evaluation of Post-Deployment Self-Improvement

Humanoid robots are becoming an important part of embodied artificial intelligence, driven by advances in reinforcement learning for locomotion, world models for prediction, and vision-language-action models for general control. However, most of these systems remain static after deployment. A policy is trained offline...

Loc X. Nguyen, Avi Deb Raha, Huy Q. Le et al. · 1 citation

CodeActionBench: Evaluating Agentic Code-as-Policy for Embodied Manipulation

CodeActionBench is introduced, a benchmark of 25 manipulation tasks that evaluates this capability through agentic Code-as-Policy and provides a controlled testbed for measuring how general-purpose models translate their capabilities into manipulation behavior and for examining typical failure scenarios in that process...

Yiheng Lyu, Xueying Jiang, Wen-Hao Li et al. · 3 citations
Sep 2026

RoboHarn-Evo: Evolving Hierarchical Physical Knowledge for Self-Improving Robotic Manipulation

RoboHarn-Evo is introduced, a dual-loop harness that evolves Hierarchical Physical Knowledge (HPK) from physical experience that demonstrates that physical interaction can be accumulated into reusable knowledge for improving subsequent manipulation.

Shi-Feng Bao, Fan-Ding Huang, Yi-Han Lin et al. · 4 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.